Advertisement

Mobile Networks and Applications

, Volume 23, Issue 4, pp 854–863 | Cite as

Improving Vehicle Localization in a Smart City with Low Cost Sensor Networks and Support Vector Machines

  • Ikram Belhajem
  • Yann Ben Maissa
  • Ahmed Tamtaoui
Article
  • 159 Downloads

Abstract

A smart city’s main purpose is to provide intelligent responses to different problems of the rapid urban population growth. For instance, integrating fleet management solutions into intelligent transportation systems (ITS) can efficiently resolve transportation problems relying on each vehicle information. Usually, the position estimate is ensured by the integration of the Global Positioning System (GPS) and Inertial Navigation Systems (INS). For multisensor data fusion, the Extended Kalman Filter (EKF) is generally applied using the sensor’s measures and the GPS position as a helper. However, the INS are expensive and require more complex computing which induces restrictions on their implementation. Furthermore, the EKF performance depends on the vehicle dynamic variations and may quickly diverge because of environmental changes. In this paper, we present a robust low cost approach using EKF and Support Vector Machines (SVM) to reliably estimate the vehicle position by limiting the EKF drawbacks. The sensors used are a GPS augmented by a low cost wireless sensor network. When GPS signals are available, we train SVM on different dynamics and outage times to learn the position errors so we can correct the future EKF predictions during GPS signal outages. We obtain empirically an improvement of up to 94% over the simple EKF predictions in case of GPS failures.

Keywords

Smart city Global positioning system Wireless sensor network Internet of things Low cost Machine learning 

Notes

Acknowledgments

This work was financially supported by the National Center of Scientific and Technical Research (CNRST), Morocco.

References

  1. 1.
    Xiong Z, Sheng H, Rong W, Cooper DE (2012) Intelligent transportation systems for smart cities: a progress review. Sci Chin Inf Sci 55:2908–2914. doi: 10.1007/s11432-012-4725-1 CrossRefGoogle Scholar
  2. 2.
    El Faouzi NE, Klein LA (2016) Data fusion for ITS: techniques and research needs. Transp Res Proced 15:495–512. doi: 10.1016/j.trpro.2016.06.042 CrossRefGoogle Scholar
  3. 3.
    De Ponte Müller F (2017) Survey on ranging sensors and cooperative techniques for relative positioning of vehicles. Sensors 17:1–27. doi: 10.3390/s17020271 CrossRefGoogle Scholar
  4. 4.
    Grewal MS (2011) Kalman filtering. Int Encyclop Statist Sci 1:705–708. doi: 10.1007/978-3-642-04898-2_321 CrossRefGoogle Scholar
  5. 5.
    Niu X, Ban Y, Zhang Q, Zhang T, Zhang H, Liu J (2015) Quantitative analysis to the impacts of IMU quality in GPS/INS deep integration. Micromachines 6:1082–1099. doi: 10.3390/mi6081082 CrossRefGoogle Scholar
  6. 6.
    Zhang H, Zhao Y (2011) The performance comparison and analysis of extended Kalman filters for GPS/DR navigation. Optik - Int J Light Electron Opt 122:777–781. doi: 10.1016/j.ijleo.2010.05.023 CrossRefGoogle Scholar
  7. 7.
    Shen Z, Georgy J, Korenberg M J, Noureldin A (2011) Low cost two dimension navigation using an augmented Kalman filter/ fast orthogonal search module for the integration of reduced inertial sensor system and global positioning system. Trans Res Part C: Emerg Technol 19:1111–1132. doi: 10.1016/j.trc.2011.01.001 CrossRefGoogle Scholar
  8. 8.
    Tamazin M, Noureldin A, Korenberg MJ, Kamel AM (2016) A new high-resolution GPS multipath mitigation technique using fast orthogonal search. J Navig 69:794–814. doi: 10.1017/s0373463315001022 CrossRefGoogle Scholar
  9. 9.
    Abd Rabbou M, El-Rabbany A (2015) Integration of GPS precise point positioning and MEMS-based INS using unscented particle filter. Sensors 15:7228–7245. doi: 10.3390/s150407228 CrossRefGoogle Scholar
  10. 10.
    Zhao Y (2014) An improved unscented particle filter with global sampling strategy. J Comput Eng :1–6. doi: 10.1155/2014/175820
  11. 11.
    Noureldin A, El-Shafie A, Bayoumi M (2011) GPS/INS Integration utilizing dynamic neural networks for vehicular navigation. Inf Fus 12:48–57. doi: 10.1016/j.inffus.2010.01.003 CrossRefGoogle Scholar
  12. 12.
    Li Z, Wang J, Li B, Gao J, Tan X (2014) GPS/INS/odometer integrated system using fuzzy neural network for land vehicle navigation applications. J Navig 67:967–983. doi: 10.1017/S0373463314000307 CrossRefGoogle Scholar
  13. 13.
    Belhajem I, Ben Maissa Y, Tamtaoui A (2017) An improved robust low cost approach for real time vehicle positioning in a smart city. Ind Netw Intell Syst :77–89. doi: 10.1007/978-3-319-52569-3_7
  14. 14.
    Belhajem I, Ben Maissa Y, Tamtaoui A (2017) A hybrid machine learning based low cost approach for real time vehicle position estimation in a smart city. Adv Ubiq Network 2:559–572. doi: 10.1007/978-981-10-1627-1_44 CrossRefGoogle Scholar
  15. 15.
    Adusumilli S, Bhatt D, Wang H, Devabhaktuni V, Bhattacharya P (2015) A novel hybrid approach utilizing principal component regression and random forest regression to bridge the period of GPS outages. Neurocomputing 166:185–192. doi: 10.1016/j.neucom.2015.03.080 CrossRefGoogle Scholar
  16. 16.
    Bhatt D, Aggarwal P, Devabhaktuni V, Bhattacharya P (2014) A novel hybrid fusion algorithm to bridge the period of GPS outages using low-cost INS. Expert Syst Appl 41:2166–2173. doi: 10.1016/j.eswa.2013.09.015 CrossRefGoogle Scholar
  17. 17.
    Chen Q, Whitbrooka A, Aickelina U, Roadknight C (2014) Data classification using the Dempster-Shafer method. J Exper Theor Artif Intell 26:493–517. doi: 10.1080/0952813X.2014.886301 CrossRefGoogle Scholar
  18. 18.
    Lucet E, Betaille D, Donnay Fleury N, Ortiz M, SALLE D, Canou J (2009) Real-time 2D localization of a car-like mobile robot using dead reckoning and GPS, with satellite masking prediction. Accur Local Land Transp Workshop :15–18Google Scholar
  19. 19.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. doi: 10.1023/A:1022627411411 zbMATHGoogle Scholar
  20. 20.
    Shawe-Taylor J, Cristianini N (2004) Pattern analysis using convex optimisation. Kernel Methods Pattern Anal. 1:195–251. doi: 10.1017/CBO9780511809682.008 CrossRefGoogle Scholar
  21. 21.
    Hsu CW, Chang CC, Lin CJ (2010) A practical guide to support vector classification. Dissertation, National Taiwan UniversityGoogle Scholar
  22. 22.
    Basak D, Pal S, Patranabis DC (2007) Support vector regression. Neural Inf Process Lett Rev 11:203–224Google Scholar
  23. 23.
    Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222. doi: 10.1023/B:STCO.0000035301.49549.88 MathSciNetCrossRefGoogle Scholar
  24. 24.
    Breiman L (2001) Random forests. Mach Learn 45:5–32. doi: 10.1023/A:1010933404324 CrossRefzbMATHGoogle Scholar
  25. 25.
    Liaw A, Wiener M (2002) Random forests. R News 2:18–22. doi: 10.7717/peerj.703/table-4 Google Scholar
  26. 26.
    Korrapati H, Courbon J, Alizon S, Marmoiton F (2013) The institut pascal data set”: un jeu de données en extérieur, multicapteurs et datées avec réalité terrain, données d’étalonnage et outils logiciels. ORASIS, Congrès des jeunes chercheurs en vision par ordinateur 1–8Google Scholar
  27. 27.
    Goodall C (2009) Improving usability of low-cost INS/GPS navigation systems using intelligent techniques. Dissertation, University of CalgaryGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Laboratory of Telecommunications, Networks and Service SystemsNational Institute of Posts and TelecommunicationsRabatMorocco

Personalised recommendations